深度学习【14】代价敏感损失函数

最新推荐文章于 2023-12-31 01:10:51 发布

DCD_Lin

最新推荐文章于 2023-12-31 01:10:51 发布

阅读量9k

点赞数 6

分类专栏：深度学习

本文链接：https://blog.youkuaiyun.com/linmingan/article/details/72830539

版权

深度学习专栏收录该内容

65 篇文章

订阅专栏

本文介绍了一种名为class-balanced sigmoid cross entropy的损失函数，该函数源自Holistically-Nested Edge Detection论文，相较于传统的交叉熵损失，它通过调整正负样本权重来解决类别不平衡问题，适用于目标检测和分割任务。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

def class_balanced_sigmoid_cross_entropy(logits, label, name='cross_entropy_loss'):
    """
    The class-balanced cross entropy loss,
    as in `Holistically-Nested Edge Detection
    <http://arxiv.org/abs/1504.06375>`_.
    This is more numerically stable than class_balanced_cross_entropy

    :param logits: size: the logits.
    :param label: size: the ground truth in {0,1}, of the same shape as logits.
    :returns: a scalar. class-balanced cross entropy loss
    """
    y = tf.cast(label, tf.float32)

    count_neg = tf.reduce_sum(1. - y) # the number of 0 in y
    count_pos = tf.reduce_sum(y) # the number of 1 in y (less than count_neg)
    beta = count_neg / (count_neg + count_pos)

    pos_weight = beta / (1 - beta)
    cost = tf.nn.weighted_cross_entropy_with_logits(logits, y, pos_weight)
    cost = tf.reduce_mean(cost * (1 - beta), name=name)

    return cost